skills/inf-sh/skills/text-to-speech/Gen Agent Trust Hub

text-to-speech

Fail

Audited by Gen Agent Trust Hub on Feb 18, 2026

Risk Level: CRITICALREMOTE_CODE_EXECUTIONEXTERNAL_DOWNLOADSCOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
  • Remote Code Execution (CRITICAL): The skill instructs the agent to execute curl -fsSL https://cli.inference.sh | sh, which is a piped remote execution pattern from an untrusted external domain. This allows a remote server to execute arbitrary code on the user's host system without any integrity checks or version pinning.
  • External Downloads (HIGH): The skill relies on binaries and scripts from inference.sh, which is not listed as a trusted organization or repository.
  • Command Execution (LOW): The skill requests permission for Bash(infsh *), which allows the agent to execute any sub-command of the infsh CLI.
  • Indirect Prompt Injection (LOW): The skill processes untrusted user-provided text for speech synthesis, creating an ingestion surface. \n- Ingestion points: The --input JSON parameter in infsh app run commands.\n- Boundary markers: Absent; there are no delimiters or instructions for the agent to ignore embedded commands in the processed text.\n- Capability inventory: The infsh command allows execution of various remote applications via the Bash tool.\n- Sanitization: No sanitization or validation of the input text is mentioned or implemented in the skill.
Recommendations
  • HIGH: Downloads and executes remote code from: https://cli.inference.sh - DO NOT USE without thorough review
  • AI detected serious security threats
Audit Metadata
Risk Level
CRITICAL
Analyzed
Feb 18, 2026, 02:00 AM